-
Notifications
You must be signed in to change notification settings - Fork 62
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Some questions about loss calculation #9
Comments
Thank you very much. And you can choose any of them to answer. |
Hi @LZDSJTU , Edit: nvm it's model.py |
@LZDSJTU the only one I've worked out so far since the code includes a comment:
|
Hi, @Ziggareto Instance Segmentation AP: [0.77272727 0.96409938 0.58364528 0.9 0.27223911 1. Looking forward your reply. |
Hi @LittleLampChen I haven't been following for ages, but I think pergroupthres.txt is generated by valid.py? Have you run that already? |
Issue 1: Issue 2: Issue 3: Issue 4: Issue 5: |
Hello, I read the code on calculating the loss and I have some questions.
line 167:
group_mat_label = tf.matmul(pts_group_label,tf.transpose(pts_group_label, perm=[0, 2, 1]))
I do not understand the meaning of this operation. Could you give an simple example for it.
line 179~184:
diffgroup_samesem_mat_label = tf.multiply(diffgroup_mat_label, samesem_mat_label)
diffgroup_diffsem_mat_label = tf.multiply(diffgroup_mat_label, diffsem_mat_label)
num_samegroup = tf.reduce_sum(samegroup_mat_label)
num_diffgroup_samesem = tf.reduce_sum(diffgroup_samesem_mat_label)
num_diffgroup_diffsem = tf.reduce_sum(diffgroup_diffsem_mat_label)
I am not clear about these code.
line 191:
pos = tf.multiply(samegroup_mat_label, pred_simmat)
I know that it want to compute the distance in the same group. But I do not know why this sentence can work. Could you provide an simple example or some equation?
line 197:
group_mask_weight = tf.matmul(group_mask, tf.transpose(group_mask, perm=[0, 2, 1]))
I think that maybe this is the same opeartion as line 167, but I cannot undestand
line 209~210:
Pr_obj = tf.reduce_sum(pts_semseg_label,axis=2)
Pr_obj = tf.cast(Pr_obj, tf.float32)
I guess that all element in Pr_obj may be 1. So what the function of it as a weight?
The text was updated successfully, but these errors were encountered: